dreaminglisted

# dreaming Turn yesterday's execution into tomorrow's leverage. This is a read-only synthesis skill. It studies recent work across repos and agent artifacts, asks better research questions, distills what was learned from project and coding execution, and writes a compact morning report. It must not mutate production code, create tickets, push branches, or expose secrets unless the user explicitly asks for a follow-up execution phase. ## Operating Shape Use `dreaming` when the work is already done or partially done and the next useful act is reflection: - after a long Codex/Claude/AO/GSD session; - after a merge request, failed branch, production incident, or agent swarm; - after work across several repos where patterns may be hidden; - before a nightly or morning research block; - when asked for "what did we learn", "what should we research", "compound insights", "dreaming", or "sleep on this". Default scope: - recent git history, dirty files, branches, and commits; - Beads, Linear references, `.planning/`, `.gsd/`, `.omc/`, handoff files, and reports; - Claude/Codex/Gemini/AO session artifacts when discoverable; - project docs such as `AGENTS.md`, `CLAUDE.md`, `README.md`, `ARCHITECTURE.md`, and existing codebase maps; - optional public research via Gemini CLI, Codex search, GitHub, docs, and X/Twitter search. ## AOSwarm Role `dreaming` is the reflection layer around AOSwarm. It does not make code changes itself. When it discovers concrete implementation work, conve